[0.7.2rc1] Updated tests, pandas code, and resolve oustanding issues

CHANGELOG.md

@@ -1,8 +1,18 @@
 # Changelog for mokapot  
 
-## [Unreleased]  
+## [0.7.2] - 2021-07-16  
+### Added  
+- `--keep_decoys` option to the command line interface. Thanks @jspaezp!
+- Notes about setting a random seed to the Python API documentation. (Issue #30)
+- Added more information about peptides that couldn't be mapped to proteins. (Issue #29) 
+
+### Fixed  
+- Loading a saved model with `mokapot.load_model()` would fail because of an
+  update to Pandas that introduced a new exception. We've updated mokapot 
+  accordingly.
+
 ### Changed  
-- Updates to unit tests.
+- Updates to unit tests. Warnings are now treated as errors for system tests.
 
 ## [0.7.1] - 2021-03-22  
 ### Changed  

docs/source/api/index.rst

@@ -1,3 +1,4 @@
+
 Python API
 ==========
 
@@ -22,6 +23,20 @@ Alternatively, PSMs that are already represented in a
 Finally, custom machine learning models can be created using the
 :py:class:`mokapot.model.Model` class.
 
+.. note::
+
+   Set your NumPy random seed to ensure reproducibility:
+
+   .. code-block::
+
+      import numpy as np
+      np.random.seed(42)
+
+   In a future release, we will update mokapot to use the `new NumPy random
+   sampling API
+   <https://numpy.org/doc/stable/reference/random/index.html?highlight=random%20sampling%20numpy%20random#module-numpy.random>`_.
+
+
 .. toctree::
    :maxdepth: 1
    :hidden:

mokapot/model.py

@@ -512,7 +512,7 @@ def load_model(model_file):
         model.is_trained = True
 
     # Then try loading it with pickle:
-    except KeyError:
+    except (KeyError, UnicodeDecodeError):
         logging.info("Loading mokapot model.")
         with open(model_file, "rb") as mod_in:
             model = pickle.load(mod_in)

mokapot/picked_protein.py

@@ -88,19 +88,19 @@ def picked_protein(
 
     if shared_unmatched:
         LOGGER.debug("%s", unmatched_prots.loc[~shared, "stripped sequence"])
-        if shared_unmatched / len(prots) > 0.10:
-            raise ValueError(
-                "Fewer than 90% of all peptides could be matched to proteins. "
-                "Verify that your digest settings are correct."
-            )
-
         LOGGER.warning(
             "%i out of %i peptides could not be mapped. "
-            "Check your digest settings.",
+            "Please check your digest settings.",
             shared_unmatched,
             len(prots),
         )
 
+        if shared_unmatched / len(prots) > 0.10:
+            raise ValueError(
+                "Fewer than 90% of all peptides could be matched to proteins. "
+                "Please verify that your digest settings are correct."
+            )
+
     # Verify that reasonable number of decoys were matched.
     if proteins.has_decoys:
         num_unmatched_decoys = unmatched_prots[target_column][~shared].sum()

tests/system_tests/test_cli.py

@@ -9,6 +9,9 @@
 import pytest
 import pandas as pd
 
+# Warnings are errors for these tests
+pytestmark = pytest.mark.filterwarnings("error")
+
 
 @pytest.fixture
 def scope_files():
@@ -78,6 +81,20 @@ def test_cli_options(tmp_path, scope_files):
         tmp_path, f"blah.{file_bases[1]}.mokapot.peptides.txt"
     ).exists()
 
+    # Test keep_decoys:
+    assert Path(
+        tmp_path, f"blah.{file_bases[0]}.mokapot.decoy.psms.txt"
+    ).exists()
+    assert Path(
+        tmp_path, f"blah.{file_bases[0]}.mokapot.decoy.peptides.txt"
+    ).exists()
+    assert Path(
+        tmp_path, f"blah.{file_bases[1]}.mokapot.decoy.psms.txt"
+    ).exists()
+    assert Path(
+        tmp_path, f"blah.{file_bases[1]}.mokapot.decoy.peptides.txt"
+    ).exists()
+
 
 def test_cli_aggregate(tmp_path, scope_files):
     """Test that aggregate results in one result file."""

tests/system_tests/test_system.py

@@ -8,11 +8,15 @@
 import os
 import logging
 
+import pytest
 import pandas as pd
 import mokapot
 
 logging.basicConfig(level=logging.INFO)
 
+# Warnings are errors for these tests
+pytestmark = pytest.mark.filterwarnings("error")
+
 
 def test_compare_to_percolator():
     """Test that mokapot get almost the same answer as Percolator"""